rocksdb/db/import_column_family_job.cc
Venki Pallipadi 22ce462450 Export Import sst files (#5495)
Summary:
Refresh of the earlier change here - https://github.com/facebook/rocksdb/issues/5135

This is a review request for code change needed for - https://github.com/facebook/rocksdb/issues/3469
"Add support for taking snapshot of a column family and creating column family from a given CF snapshot"

We have an implementation for this that we have been testing internally. We have two new APIs that together provide this functionality.

(1) ExportColumnFamily() - This API is modelled after CreateCheckpoint() as below.
// Exports all live SST files of a specified Column Family onto export_dir,
// returning SST files information in metadata.
// - SST files will be created as hard links when the directory specified
//   is in the same partition as the db directory, copied otherwise.
// - export_dir should not already exist and will be created by this API.
// - Always triggers a flush.
virtual Status ExportColumnFamily(ColumnFamilyHandle* handle,
                                  const std::string& export_dir,
                                  ExportImportFilesMetaData** metadata);

Internally, the API will DisableFileDeletions(), GetColumnFamilyMetaData(), Parse through
metadata, creating links/copies of all the sst files, EnableFileDeletions() and complete the call by
returning the list of file metadata.

(2) CreateColumnFamilyWithImport() - This API is modeled after IngestExternalFile(), but invoked only during a CF creation as below.
// CreateColumnFamilyWithImport() will create a new column family with
// column_family_name and import external SST files specified in metadata into
// this column family.
// (1) External SST files can be created using SstFileWriter.
// (2) External SST files can be exported from a particular column family in
//     an existing DB.
// Option in import_options specifies whether the external files are copied or
// moved (default is copy). When option specifies copy, managing files at
// external_file_path is caller's responsibility. When option specifies a
// move, the call ensures that the specified files at external_file_path are
// deleted on successful return and files are not modified on any error
// return.
// On error return, column family handle returned will be nullptr.
// ColumnFamily will be present on successful return and will not be present
// on error return. ColumnFamily may be present on any crash during this call.
virtual Status CreateColumnFamilyWithImport(
    const ColumnFamilyOptions& options, const std::string& column_family_name,
    const ImportColumnFamilyOptions& import_options,
    const ExportImportFilesMetaData& metadata,
    ColumnFamilyHandle** handle);

Internally, this API creates a new CF, parses all the sst files and adds it to the specified column family, at the same level and with same sequence number as in the metadata. Also performs safety checks with respect to overlaps between the sst files being imported.

If incoming sequence number is higher than current local sequence number, local sequence
number is updated to reflect this.

Note, as the sst files is are being moved across Column Families, Column Family name in sst file
will no longer match the actual column family on destination DB. The API does not modify Column
Family name or id in the sst files being imported.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5495

Differential Revision: D16018881

fbshipit-source-id: 9ae2251025d5916d35a9fc4ea4d6707f6be16ff9
2019-07-17 12:27:14 -07:00

258 lines
8.7 KiB
C++

#ifndef ROCKSDB_LITE
#include "db/import_column_family_job.h"
#include <cinttypes>
#include <algorithm>
#include <string>
#include <vector>
#include "db/version_edit.h"
#include "file/file_util.h"
#include "table/merging_iterator.h"
#include "table/scoped_arena_iterator.h"
#include "table/sst_file_writer_collectors.h"
#include "table/table_builder.h"
#include "util/file_reader_writer.h"
#include "util/stop_watch.h"
namespace rocksdb {
Status ImportColumnFamilyJob::Prepare(uint64_t next_file_number,
SuperVersion* sv) {
Status status;
// Read the information of files we are importing
for (const auto& file_metadata : metadata_) {
const auto file_path = file_metadata.db_path + "/" + file_metadata.name;
IngestedFileInfo file_to_import;
status = GetIngestedFileInfo(file_path, &file_to_import, sv);
if (!status.ok()) {
return status;
}
files_to_import_.push_back(file_to_import);
}
const auto ucmp = cfd_->internal_comparator().user_comparator();
auto num_files = files_to_import_.size();
if (num_files == 0) {
return Status::InvalidArgument("The list of files is empty");
} else if (num_files > 1) {
// Verify that passed files don't have overlapping ranges in any particular
// level.
int min_level = 1; // Check for overlaps in Level 1 and above.
int max_level = -1;
for (const auto& file_metadata : metadata_) {
if (file_metadata.level > max_level) {
max_level = file_metadata.level;
}
}
for (int level = min_level; level <= max_level; ++level) {
autovector<const IngestedFileInfo*> sorted_files;
for (size_t i = 0; i < num_files; i++) {
if (metadata_[i].level == level) {
sorted_files.push_back(&files_to_import_[i]);
}
}
std::sort(sorted_files.begin(), sorted_files.end(),
[&ucmp](const IngestedFileInfo* info1,
const IngestedFileInfo* info2) {
return ucmp->Compare(info1->smallest_user_key,
info2->smallest_user_key) < 0;
});
for (size_t i = 0; i < sorted_files.size() - 1; i++) {
if (ucmp->Compare(sorted_files[i]->largest_user_key,
sorted_files[i + 1]->smallest_user_key) >= 0) {
return Status::InvalidArgument("Files have overlapping ranges");
}
}
}
}
for (const auto& f : files_to_import_) {
if (f.num_entries == 0) {
return Status::InvalidArgument("File contain no entries");
}
if (!f.smallest_internal_key().Valid() ||
!f.largest_internal_key().Valid()) {
return Status::Corruption("File has corrupted keys");
}
}
// Copy/Move external files into DB
auto hardlink_files = import_options_.move_files;
for (auto& f : files_to_import_) {
f.fd = FileDescriptor(next_file_number++, 0, f.file_size);
const auto path_outside_db = f.external_file_path;
const auto path_inside_db = TableFileName(
cfd_->ioptions()->cf_paths, f.fd.GetNumber(), f.fd.GetPathId());
if (hardlink_files) {
status = env_->LinkFile(path_outside_db, path_inside_db);
if (status.IsNotSupported()) {
// Original file is on a different FS, use copy instead of hard linking
hardlink_files = false;
}
}
if (!hardlink_files) {
status = CopyFile(env_, path_outside_db, path_inside_db, 0,
db_options_.use_fsync);
}
if (!status.ok()) {
break;
}
f.copy_file = !hardlink_files;
f.internal_file_path = path_inside_db;
}
if (!status.ok()) {
// We failed, remove all files that we copied into the db
for (const auto& f : files_to_import_) {
if (f.internal_file_path.empty()) {
break;
}
const auto s = env_->DeleteFile(f.internal_file_path);
if (!s.ok()) {
ROCKS_LOG_WARN(db_options_.info_log,
"AddFile() clean up for file %s failed : %s",
f.internal_file_path.c_str(), s.ToString().c_str());
}
}
}
return status;
}
// REQUIRES: we have become the only writer by entering both write_thread_ and
// nonmem_write_thread_
Status ImportColumnFamilyJob::Run() {
Status status;
edit_.SetColumnFamily(cfd_->GetID());
for (size_t i = 0; i < files_to_import_.size(); ++i) {
const auto& f = files_to_import_[i];
const auto& file_metadata = metadata_[i];
edit_.AddFile(file_metadata.level, f.fd.GetNumber(), f.fd.GetPathId(),
f.fd.GetFileSize(), f.smallest_internal_key(),
f.largest_internal_key(), file_metadata.smallest_seqno,
file_metadata.largest_seqno, false);
// If incoming sequence number is higher, update local sequence number.
if (file_metadata.largest_seqno > versions_->LastSequence()) {
versions_->SetLastAllocatedSequence(file_metadata.largest_seqno);
versions_->SetLastPublishedSequence(file_metadata.largest_seqno);
versions_->SetLastSequence(file_metadata.largest_seqno);
}
}
return status;
}
void ImportColumnFamilyJob::Cleanup(const Status& status) {
if (!status.ok()) {
// We failed to add files to the database remove all the files we copied.
for (const auto& f : files_to_import_) {
const auto s = env_->DeleteFile(f.internal_file_path);
if (!s.ok()) {
ROCKS_LOG_WARN(db_options_.info_log,
"AddFile() clean up for file %s failed : %s",
f.internal_file_path.c_str(), s.ToString().c_str());
}
}
} else if (status.ok() && import_options_.move_files) {
// The files were moved and added successfully, remove original file links
for (IngestedFileInfo& f : files_to_import_) {
const auto s = env_->DeleteFile(f.external_file_path);
if (!s.ok()) {
ROCKS_LOG_WARN(
db_options_.info_log,
"%s was added to DB successfully but failed to remove original "
"file link : %s",
f.external_file_path.c_str(), s.ToString().c_str());
}
}
}
}
Status ImportColumnFamilyJob::GetIngestedFileInfo(
const std::string& external_file, IngestedFileInfo* file_to_import,
SuperVersion* sv) {
file_to_import->external_file_path = external_file;
// Get external file size
auto status = env_->GetFileSize(external_file, &file_to_import->file_size);
if (!status.ok()) {
return status;
}
// Create TableReader for external file
std::unique_ptr<TableReader> table_reader;
std::unique_ptr<RandomAccessFile> sst_file;
std::unique_ptr<RandomAccessFileReader> sst_file_reader;
status = env_->NewRandomAccessFile(external_file, &sst_file, env_options_);
if (!status.ok()) {
return status;
}
sst_file_reader.reset(new RandomAccessFileReader(std::move(sst_file),
external_file));
status = cfd_->ioptions()->table_factory->NewTableReader(
TableReaderOptions(*cfd_->ioptions(),
sv->mutable_cf_options.prefix_extractor.get(),
env_options_, cfd_->internal_comparator()),
std::move(sst_file_reader), file_to_import->file_size, &table_reader);
if (!status.ok()) {
return status;
}
// Get the external file properties
auto props = table_reader->GetTableProperties();
// Set original_seqno to 0.
file_to_import->original_seqno = 0;
// Get number of entries in table
file_to_import->num_entries = props->num_entries;
ParsedInternalKey key;
ReadOptions ro;
// During reading the external file we can cache blocks that we read into
// the block cache, if we later change the global seqno of this file, we will
// have block in cache that will include keys with wrong seqno.
// We need to disable fill_cache so that we read from the file without
// updating the block cache.
ro.fill_cache = false;
std::unique_ptr<InternalIterator> iter(table_reader->NewIterator(
ro, sv->mutable_cf_options.prefix_extractor.get(), /*arena=*/nullptr,
/*skip_filters=*/false, TableReaderCaller::kExternalSSTIngestion));
// Get first (smallest) key from file
iter->SeekToFirst();
if (!ParseInternalKey(iter->key(), &key)) {
return Status::Corruption("external file have corrupted keys");
}
file_to_import->smallest_user_key = key.user_key.ToString();
// Get last (largest) key from file
iter->SeekToLast();
if (!ParseInternalKey(iter->key(), &key)) {
return Status::Corruption("external file have corrupted keys");
}
file_to_import->largest_user_key = key.user_key.ToString();
file_to_import->cf_id = static_cast<uint32_t>(props->column_family_id);
file_to_import->table_properties = *props;
return status;
}
} // namespace rocksdb
#endif // !ROCKSDB_LITE